| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 372000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.375e-06, | |
| "loss": 6.8546, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.875e-05, | |
| "loss": 5.3571, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.8125e-05, | |
| "loss": 5.0355, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.75e-05, | |
| "loss": 4.8077, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.6874999999999994e-05, | |
| "loss": 4.6389, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.625e-05, | |
| "loss": 4.4944, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.5625e-05, | |
| "loss": 4.3811, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.5e-05, | |
| "loss": 4.2867, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.437499999999999e-05, | |
| "loss": 4.2018, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.374999999999999e-05, | |
| "loss": 4.126, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000103115625, | |
| "loss": 4.0645, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.000112490625, | |
| "loss": 4.005, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.000121865625, | |
| "loss": 3.9411, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00013123125, | |
| "loss": 3.889, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.000140596875, | |
| "loss": 3.8468, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0001499625, | |
| "loss": 3.8099, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.000159328125, | |
| "loss": 3.7701, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.000168703125, | |
| "loss": 3.7444, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.34515730881026885, | |
| "eval_loss": 3.9303231239318848, | |
| "eval_runtime": 153.4286, | |
| "eval_samples_per_second": 377.492, | |
| "eval_steps_per_second": 5.899, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.000178078125, | |
| "loss": 3.7026, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00018745312499999998, | |
| "loss": 3.676, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00019681874999999998, | |
| "loss": 3.6595, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00020619374999999998, | |
| "loss": 3.6375, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00021555937499999998, | |
| "loss": 3.6166, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00022493437499999998, | |
| "loss": 3.6019, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00023430937499999997, | |
| "loss": 3.5891, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00024368437499999997, | |
| "loss": 3.57, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00025305, | |
| "loss": 3.5536, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.000262425, | |
| "loss": 3.544, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.000271790625, | |
| "loss": 3.5305, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.000281165625, | |
| "loss": 3.5216, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.000290540625, | |
| "loss": 3.5093, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00029990624999999993, | |
| "loss": 3.5018, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00029912647058823525, | |
| "loss": 3.4851, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.000298245, | |
| "loss": 3.4713, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002973626470588235, | |
| "loss": 3.459, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.000296480294117647, | |
| "loss": 3.4466, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00029559794117647056, | |
| "loss": 3.4367, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3746240995756378, | |
| "eval_loss": 3.637483596801758, | |
| "eval_runtime": 155.3554, | |
| "eval_samples_per_second": 372.81, | |
| "eval_steps_per_second": 5.825, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002947155882352941, | |
| "loss": 3.3868, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0002938341176470588, | |
| "loss": 3.3768, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00029295176470588234, | |
| "loss": 3.3733, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0002920694117647058, | |
| "loss": 3.3685, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00029118794117647057, | |
| "loss": 3.3617, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00029030558823529406, | |
| "loss": 3.3563, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002894241176470588, | |
| "loss": 3.3446, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00028854176470588234, | |
| "loss": 3.3428, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00028766029411764703, | |
| "loss": 3.3408, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002867779411764706, | |
| "loss": 3.3363, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002858955882352941, | |
| "loss": 3.3302, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00028501323529411766, | |
| "loss": 3.3205, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002841317647058823, | |
| "loss": 3.3202, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00028324941176470584, | |
| "loss": 3.3153, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002823670588235294, | |
| "loss": 3.3082, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.00028148558823529407, | |
| "loss": 3.3033, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0002806032352941176, | |
| "loss": 3.298, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00027972176470588236, | |
| "loss": 3.29, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.38803887906463225, | |
| "eval_loss": 3.5155463218688965, | |
| "eval_runtime": 155.2596, | |
| "eval_samples_per_second": 373.04, | |
| "eval_steps_per_second": 5.829, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00027883941176470585, | |
| "loss": 3.2763, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0002779570588235294, | |
| "loss": 3.2269, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0002770755882352941, | |
| "loss": 3.2265, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.0002761932352941176, | |
| "loss": 3.2255, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0002753117647058823, | |
| "loss": 3.2326, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.00027442941176470585, | |
| "loss": 3.2239, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0002735470588235294, | |
| "loss": 3.2301, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0002726655882352941, | |
| "loss": 3.2253, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.00027178323529411763, | |
| "loss": 3.2214, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00027090088235294117, | |
| "loss": 3.2241, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.00027001941176470586, | |
| "loss": 3.2196, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00026913705882352935, | |
| "loss": 3.2222, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0002682547058823529, | |
| "loss": 3.2175, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.00026737323529411763, | |
| "loss": 3.2146, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0002664908823529411, | |
| "loss": 3.2127, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.00026560941176470587, | |
| "loss": 3.2124, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0002647270588235294, | |
| "loss": 3.2123, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.0002638455882352941, | |
| "loss": 3.2077, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00026296323529411764, | |
| "loss": 3.2081, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3940327953259559, | |
| "eval_loss": 3.475128412246704, | |
| "eval_runtime": 154.8524, | |
| "eval_samples_per_second": 374.021, | |
| "eval_steps_per_second": 5.844, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0002620808823529412, | |
| "loss": 3.1625, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0002611994117647058, | |
| "loss": 3.1382, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00026031705882352936, | |
| "loss": 3.1446, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0002594347058823529, | |
| "loss": 3.1452, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00025855235294117645, | |
| "loss": 3.1449, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00025767088235294114, | |
| "loss": 3.1535, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.0002567894117647059, | |
| "loss": 3.1498, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0002559070588235294, | |
| "loss": 3.1478, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.0002550247058823529, | |
| "loss": 3.1472, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.00025414235294117645, | |
| "loss": 3.1502, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.00025325999999999994, | |
| "loss": 3.1471, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.0002523785294117647, | |
| "loss": 3.1488, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.00025149617647058823, | |
| "loss": 3.1472, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0002506138235294117, | |
| "loss": 3.1535, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.00024973235294117646, | |
| "loss": 3.1546, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.00024885, | |
| "loss": 3.1469, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0002479685294117647, | |
| "loss": 3.15, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00024708617647058824, | |
| "loss": 3.1455, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0002462047058823529, | |
| "loss": 3.1438, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.398348033440005, | |
| "eval_loss": 3.419024705886841, | |
| "eval_runtime": 154.8451, | |
| "eval_samples_per_second": 374.038, | |
| "eval_steps_per_second": 5.845, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0002453223529411764, | |
| "loss": 3.0764, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.00024443999999999996, | |
| "loss": 3.0808, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0002435576470588235, | |
| "loss": 3.0854, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.0002426770588235294, | |
| "loss": 3.0928, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00024179470588235293, | |
| "loss": 3.0894, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.00024091323529411765, | |
| "loss": 3.0909, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.00024003088235294116, | |
| "loss": 3.0971, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00023914941176470585, | |
| "loss": 3.0979, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.00023826705882352937, | |
| "loss": 3.1, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.0002373847058823529, | |
| "loss": 3.0951, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.00023650235294117645, | |
| "loss": 3.0994, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.00023562088235294114, | |
| "loss": 3.0989, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.00023473852941176469, | |
| "loss": 3.1001, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.00023385617647058823, | |
| "loss": 3.0974, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.00023297382352941174, | |
| "loss": 3.0927, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.00023209235294117646, | |
| "loss": 3.0977, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.00023121, | |
| "loss": 3.102, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0002303276470588235, | |
| "loss": 3.0947, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.40218399473400135, | |
| "eval_loss": 3.3905391693115234, | |
| "eval_runtime": 155.1728, | |
| "eval_samples_per_second": 373.248, | |
| "eval_steps_per_second": 5.832, | |
| "step": 111600 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0002294461764705882, | |
| "loss": 3.0704, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.00022856382352941175, | |
| "loss": 3.031, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.00022768235294117644, | |
| "loss": 3.0337, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.00022679999999999998, | |
| "loss": 3.0437, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.00022591764705882353, | |
| "loss": 3.0462, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.00022503617647058822, | |
| "loss": 3.0505, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 0.00022415382352941176, | |
| "loss": 3.0507, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00022327235294117645, | |
| "loss": 3.0527, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.00022238999999999996, | |
| "loss": 3.0526, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.0002215076470588235, | |
| "loss": 3.0515, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.00022062617647058822, | |
| "loss": 3.0496, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 0.0002197447058823529, | |
| "loss": 3.0517, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00021886235294117645, | |
| "loss": 3.0625, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00021798, | |
| "loss": 3.0565, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.0002170976470588235, | |
| "loss": 3.0602, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.00021621617647058823, | |
| "loss": 3.0597, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.00021533470588235292, | |
| "loss": 3.0591, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.00021445235294117643, | |
| "loss": 3.0612, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.00021356999999999998, | |
| "loss": 3.0569, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.40292205685134075, | |
| "eval_loss": 3.3831627368927, | |
| "eval_runtime": 154.6364, | |
| "eval_samples_per_second": 374.543, | |
| "eval_steps_per_second": 5.852, | |
| "step": 130200 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.00021268764705882352, | |
| "loss": 3.0044, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.00021180529411764704, | |
| "loss": 2.9984, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.00021092382352941175, | |
| "loss": 2.9983, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.0002100414705882353, | |
| "loss": 3.0072, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.0002091591176470588, | |
| "loss": 3.013, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.00020827764705882353, | |
| "loss": 3.0085, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.00020739529411764701, | |
| "loss": 3.009, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.00020651382352941173, | |
| "loss": 3.0152, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.00020563147058823527, | |
| "loss": 3.0172, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.0002047491176470588, | |
| "loss": 3.0198, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.0002038676470588235, | |
| "loss": 3.0207, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.00020298529411764705, | |
| "loss": 3.0238, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.0002021029411764706, | |
| "loss": 3.0222, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.00020122147058823528, | |
| "loss": 3.0237, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.00020033911764705882, | |
| "loss": 3.0225, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.00019945852941176468, | |
| "loss": 3.0232, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 0.0001985761764705882, | |
| "loss": 3.0275, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.00019769382352941174, | |
| "loss": 3.029, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.40509459032581013, | |
| "eval_loss": 3.3739943504333496, | |
| "eval_runtime": 154.5594, | |
| "eval_samples_per_second": 374.73, | |
| "eval_steps_per_second": 5.855, | |
| "step": 148800 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0001968114705882353, | |
| "loss": 3.0145, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.00019592999999999998, | |
| "loss": 2.9607, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.00019504764705882352, | |
| "loss": 2.9717, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 0.00019416529411764706, | |
| "loss": 2.9732, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.00019328382352941175, | |
| "loss": 2.977, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.00019240147058823527, | |
| "loss": 2.974, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.00019151911764705878, | |
| "loss": 2.9822, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.00019063676470588233, | |
| "loss": 2.9825, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.00018975529411764704, | |
| "loss": 2.9837, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 0.00018887294117647058, | |
| "loss": 2.9869, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.00018799147058823527, | |
| "loss": 2.9899, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 0.00018710911764705882, | |
| "loss": 2.9881, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.00018622676470588236, | |
| "loss": 2.9899, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.00018534441176470588, | |
| "loss": 2.9893, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.00018446294117647056, | |
| "loss": 2.9917, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.00018358147058823528, | |
| "loss": 2.9931, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.0001826991176470588, | |
| "loss": 2.995, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.00018181676470588234, | |
| "loss": 2.9965, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 0.00018093441176470585, | |
| "loss": 2.9953, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.40588418108360097, | |
| "eval_loss": 3.3781139850616455, | |
| "eval_runtime": 155.1788, | |
| "eval_samples_per_second": 373.234, | |
| "eval_steps_per_second": 5.832, | |
| "step": 167400 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.0001800520588235294, | |
| "loss": 2.9607, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.00017916970588235294, | |
| "loss": 2.9343, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00017828823529411763, | |
| "loss": 2.94, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.00017740588235294117, | |
| "loss": 2.9503, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.00017652441176470586, | |
| "loss": 2.9435, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.00017564205882352938, | |
| "loss": 2.954, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 0.0001747605882352941, | |
| "loss": 2.9553, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 0.00017387823529411764, | |
| "loss": 2.9573, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 0.00017299588235294115, | |
| "loss": 2.9569, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.0001721135294117647, | |
| "loss": 2.9613, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.0001712320588235294, | |
| "loss": 2.9613, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.00017034970588235293, | |
| "loss": 2.9651, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.00016946823529411762, | |
| "loss": 2.9647, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 0.00016858588235294116, | |
| "loss": 2.9642, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.00016770352941176467, | |
| "loss": 2.9664, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0001668220588235294, | |
| "loss": 2.9679, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.00016593970588235293, | |
| "loss": 2.9668, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00016505735294117645, | |
| "loss": 2.9655, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00016417588235294117, | |
| "loss": 2.9667, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.40691334306935756, | |
| "eval_loss": 3.3879029750823975, | |
| "eval_runtime": 154.9035, | |
| "eval_samples_per_second": 373.897, | |
| "eval_steps_per_second": 5.842, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 0.0001632935294117647, | |
| "loss": 2.904, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.00016241117647058822, | |
| "loss": 2.9111, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.0001615297058823529, | |
| "loss": 2.915, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.00016064735294117646, | |
| "loss": 2.9198, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.00015976588235294114, | |
| "loss": 2.9215, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 0.0001588835294117647, | |
| "loss": 2.9301, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.00015800117647058823, | |
| "loss": 2.9329, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.00015711970588235292, | |
| "loss": 2.9325, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.00015623735294117646, | |
| "loss": 2.9347, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 0.000155355, | |
| "loss": 2.9338, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 0.00015447264705882352, | |
| "loss": 2.9341, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0001535911764705882, | |
| "loss": 2.9439, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 0.00015270882352941173, | |
| "loss": 2.9439, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 0.00015182735294117644, | |
| "loss": 2.9419, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.00015094499999999999, | |
| "loss": 2.9381, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.00015006264705882353, | |
| "loss": 2.9431, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 0.00014918029411764704, | |
| "loss": 2.9435, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.00014829882352941176, | |
| "loss": 2.9426, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4070695413601653, | |
| "eval_loss": 3.376622438430786, | |
| "eval_runtime": 154.8354, | |
| "eval_samples_per_second": 374.062, | |
| "eval_steps_per_second": 5.845, | |
| "step": 204600 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.00014741735294117645, | |
| "loss": 2.918, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.000146535, | |
| "loss": 2.8858, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.0001456535294117647, | |
| "loss": 2.8906, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 0.00014477117647058822, | |
| "loss": 2.8937, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.00014388882352941174, | |
| "loss": 2.9007, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.00014300647058823528, | |
| "loss": 2.8996, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 0.000142125, | |
| "loss": 2.9052, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.00014124264705882351, | |
| "loss": 2.9059, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 0.0001403611764705882, | |
| "loss": 2.9084, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.00013947882352941175, | |
| "loss": 2.9092, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.0001385964705882353, | |
| "loss": 2.915, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 0.000137715, | |
| "loss": 2.9136, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 0.00013683264705882352, | |
| "loss": 2.9149, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.00013595029411764704, | |
| "loss": 2.9185, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 0.00013506882352941175, | |
| "loss": 2.9194, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.0001341864705882353, | |
| "loss": 2.9203, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 0.0001333041176470588, | |
| "loss": 2.9234, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.0001324226470588235, | |
| "loss": 2.9217, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 0.00013154029411764704, | |
| "loss": 2.9217, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.40853243072891327, | |
| "eval_loss": 3.3643746376037598, | |
| "eval_runtime": 154.7928, | |
| "eval_samples_per_second": 374.165, | |
| "eval_steps_per_second": 5.847, | |
| "step": 223200 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 0.0001306579411764706, | |
| "loss": 2.8752, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.0001297755882352941, | |
| "loss": 2.8662, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 0.00012889323529411765, | |
| "loss": 2.8742, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 0.0001280126470588235, | |
| "loss": 2.8765, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 0.00012713029411764705, | |
| "loss": 2.8786, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 0.00012624882352941177, | |
| "loss": 2.8818, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.00012536647058823528, | |
| "loss": 2.8831, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 0.0001244841176470588, | |
| "loss": 2.8812, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 0.00012360264705882351, | |
| "loss": 2.8865, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 0.00012272029411764706, | |
| "loss": 2.8874, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 0.00012183794117647059, | |
| "loss": 2.8898, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 0.00012095558823529412, | |
| "loss": 2.8919, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 0.0001200741176470588, | |
| "loss": 2.8975, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 0.00011919176470588235, | |
| "loss": 2.8972, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.00011831029411764705, | |
| "loss": 2.8976, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 0.00011742794117647058, | |
| "loss": 2.9018, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.0001165455882352941, | |
| "loss": 2.8994, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 0.00011566411764705881, | |
| "loss": 2.8993, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.40817650017205326, | |
| "eval_loss": 3.3694441318511963, | |
| "eval_runtime": 154.6531, | |
| "eval_samples_per_second": 374.503, | |
| "eval_steps_per_second": 5.852, | |
| "step": 241800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 0.00011478176470588234, | |
| "loss": 2.8887, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 0.00011389941176470588, | |
| "loss": 2.8461, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 0.0001130170588235294, | |
| "loss": 2.8513, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 0.0001121355882352941, | |
| "loss": 2.856, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.00011125411764705882, | |
| "loss": 2.8574, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00011037176470588235, | |
| "loss": 2.859, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.00010948941176470588, | |
| "loss": 2.8599, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 0.00010860794117647058, | |
| "loss": 2.867, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 0.00010772558823529411, | |
| "loss": 2.8631, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 0.00010684323529411764, | |
| "loss": 2.8676, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.00010596088235294117, | |
| "loss": 2.8709, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 0.00010507941176470587, | |
| "loss": 2.8697, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 0.0001041970588235294, | |
| "loss": 2.8746, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.00010331470588235293, | |
| "loss": 2.8754, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 0.00010243323529411765, | |
| "loss": 2.8773, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 0.00010155088235294116, | |
| "loss": 2.8724, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 0.00010066852941176469, | |
| "loss": 2.8786, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 9.978617647058822e-05, | |
| "loss": 2.8808, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 9.890382352941176e-05, | |
| "loss": 2.8758, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4088403261124711, | |
| "eval_loss": 3.386643886566162, | |
| "eval_runtime": 154.4069, | |
| "eval_samples_per_second": 375.1, | |
| "eval_steps_per_second": 5.861, | |
| "step": 260400 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 9.802235294117647e-05, | |
| "loss": 2.8446, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 9.714088235294117e-05, | |
| "loss": 2.8291, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 9.62585294117647e-05, | |
| "loss": 2.8344, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 9.537705882352941e-05, | |
| "loss": 2.8359, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 9.449470588235294e-05, | |
| "loss": 2.8377, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 9.361235294117646e-05, | |
| "loss": 2.8413, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 9.273088235294116e-05, | |
| "loss": 2.8432, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 9.18485294117647e-05, | |
| "loss": 2.8471, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 9.096617647058823e-05, | |
| "loss": 2.8443, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 9.008382352941176e-05, | |
| "loss": 2.8479, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 8.920235294117645e-05, | |
| "loss": 2.8513, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 8.832e-05, | |
| "loss": 2.8549, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 8.743941176470588e-05, | |
| "loss": 2.8546, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 8.65570588235294e-05, | |
| "loss": 2.8584, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 8.567470588235293e-05, | |
| "loss": 2.8543, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 8.479235294117646e-05, | |
| "loss": 2.8597, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 8.391088235294117e-05, | |
| "loss": 2.8591, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 8.302941176470588e-05, | |
| "loss": 2.8617, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 8.21470588235294e-05, | |
| "loss": 2.8544, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4086822467239676, | |
| "eval_loss": 3.384922504425049, | |
| "eval_runtime": 154.8421, | |
| "eval_samples_per_second": 374.046, | |
| "eval_steps_per_second": 5.845, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 8.12664705882353e-05, | |
| "loss": 2.8106, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 8.038411764705882e-05, | |
| "loss": 2.8126, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 7.950176470588235e-05, | |
| "loss": 2.8172, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 7.861941176470587e-05, | |
| "loss": 2.8257, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 7.77370588235294e-05, | |
| "loss": 2.8198, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 7.685558823529411e-05, | |
| "loss": 2.8253, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 7.597323529411764e-05, | |
| "loss": 2.8255, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 7.509176470588235e-05, | |
| "loss": 2.8325, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 7.420941176470588e-05, | |
| "loss": 2.8319, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 7.332794117647058e-05, | |
| "loss": 2.8316, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 7.244558823529411e-05, | |
| "loss": 2.8325, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 7.156323529411764e-05, | |
| "loss": 2.835, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 7.068088235294117e-05, | |
| "loss": 2.8365, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 6.97985294117647e-05, | |
| "loss": 2.8328, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 6.891705882352941e-05, | |
| "loss": 2.834, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 6.803470588235293e-05, | |
| "loss": 2.8412, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 6.715323529411764e-05, | |
| "loss": 2.8342, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 6.627088235294117e-05, | |
| "loss": 2.8363, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4085711947778578, | |
| "eval_loss": 3.4028050899505615, | |
| "eval_runtime": 154.624, | |
| "eval_samples_per_second": 374.573, | |
| "eval_steps_per_second": 5.853, | |
| "step": 297600 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 6.538941176470588e-05, | |
| "loss": 2.8225, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 6.45070588235294e-05, | |
| "loss": 2.7936, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 6.362470588235293e-05, | |
| "loss": 2.8004, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 6.274323529411764e-05, | |
| "loss": 2.8005, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 6.186088235294117e-05, | |
| "loss": 2.8083, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 6.09785294117647e-05, | |
| "loss": 2.8083, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 6.0097058823529405e-05, | |
| "loss": 2.8047, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 5.921470588235294e-05, | |
| "loss": 2.8067, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 5.8332352941176464e-05, | |
| "loss": 2.8139, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 5.7449999999999994e-05, | |
| "loss": 2.8145, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 5.6568529411764696e-05, | |
| "loss": 2.8164, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 5.568705882352941e-05, | |
| "loss": 2.8113, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 5.4804705882352935e-05, | |
| "loss": 2.8179, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 5.3923235294117644e-05, | |
| "loss": 2.819, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 5.3040882352941166e-05, | |
| "loss": 2.816, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 5.21585294117647e-05, | |
| "loss": 2.8201, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "learning_rate": 5.127617647058823e-05, | |
| "loss": 2.8151, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 5.0394705882352935e-05, | |
| "loss": 2.819, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 4.951235294117647e-05, | |
| "loss": 2.8222, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.40890569425739837, | |
| "eval_loss": 3.3989803791046143, | |
| "eval_runtime": 154.6683, | |
| "eval_samples_per_second": 374.466, | |
| "eval_steps_per_second": 5.851, | |
| "step": 316200 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 4.8629999999999993e-05, | |
| "loss": 2.7864, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 4.774764705882353e-05, | |
| "loss": 2.7845, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 4.6867058823529405e-05, | |
| "loss": 2.7865, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 4.598470588235294e-05, | |
| "loss": 2.7893, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 4.5103235294117643e-05, | |
| "loss": 2.788, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 4.422088235294117e-05, | |
| "loss": 2.7909, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 4.33385294117647e-05, | |
| "loss": 2.7889, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 4.245617647058823e-05, | |
| "loss": 2.7943, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 4.157382352941177e-05, | |
| "loss": 2.7979, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 4.069235294117647e-05, | |
| "loss": 2.7969, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 3.981e-05, | |
| "loss": 2.7966, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 3.892764705882352e-05, | |
| "loss": 2.802, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 3.804529411764706e-05, | |
| "loss": 2.7987, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 3.716382352941176e-05, | |
| "loss": 2.7979, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 3.6282352941176464e-05, | |
| "loss": 2.7976, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 3.540088235294117e-05, | |
| "loss": 2.8026, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 3.45185294117647e-05, | |
| "loss": 2.798, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 3.363617647058823e-05, | |
| "loss": 2.8018, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4095525903185545, | |
| "eval_loss": 3.398442029953003, | |
| "eval_runtime": 155.2345, | |
| "eval_samples_per_second": 373.1, | |
| "eval_steps_per_second": 5.83, | |
| "step": 334800 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.275382352941176e-05, | |
| "loss": 2.7957, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 3.187147058823529e-05, | |
| "loss": 2.7702, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 3.099e-05, | |
| "loss": 2.7682, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 3.0108529411764705e-05, | |
| "loss": 2.7714, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 2.9226176470588235e-05, | |
| "loss": 2.7758, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 2.834382352941176e-05, | |
| "loss": 2.7784, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 2.746147058823529e-05, | |
| "loss": 2.7762, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 2.6579117647058823e-05, | |
| "loss": 2.779, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 2.5697647058823526e-05, | |
| "loss": 2.7778, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 2.481529411764706e-05, | |
| "loss": 2.7852, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 2.3932941176470588e-05, | |
| "loss": 2.7799, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 2.3050588235294114e-05, | |
| "loss": 2.7818, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 2.2169117647058823e-05, | |
| "loss": 2.7816, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 2.128764705882353e-05, | |
| "loss": 2.7822, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 2.040529411764706e-05, | |
| "loss": 2.7823, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 1.9522941176470585e-05, | |
| "loss": 2.7791, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 1.8640588235294117e-05, | |
| "loss": 2.7863, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 1.7759117647058823e-05, | |
| "loss": 2.784, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 1.6876764705882353e-05, | |
| "loss": 2.7834, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4090608848172977, | |
| "eval_loss": 3.4143290519714355, | |
| "eval_runtime": 154.3909, | |
| "eval_samples_per_second": 375.139, | |
| "eval_steps_per_second": 5.862, | |
| "step": 353400 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 1.599529411764706e-05, | |
| "loss": 2.7704, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 1.5113823529411762e-05, | |
| "loss": 2.7643, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 1.4231470588235294e-05, | |
| "loss": 2.7622, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 1.3349117647058821e-05, | |
| "loss": 2.7693, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 1.2466764705882353e-05, | |
| "loss": 2.7638, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 1.158441176470588e-05, | |
| "loss": 2.7635, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 1.0702058823529411e-05, | |
| "loss": 2.7606, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 9.820588235294115e-06, | |
| "loss": 2.7663, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 19.46, | |
| "learning_rate": 8.938235294117647e-06, | |
| "loss": 2.7634, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 8.056764705882352e-06, | |
| "loss": 2.7638, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 7.175294117647058e-06, | |
| "loss": 2.7667, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 6.2929411764705876e-06, | |
| "loss": 2.7678, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 5.411470588235293e-06, | |
| "loss": 2.7655, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 4.529117647058823e-06, | |
| "loss": 2.7639, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 3.6467647058823527e-06, | |
| "loss": 2.7684, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 2.765294117647059e-06, | |
| "loss": 2.7625, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 1.882941176470588e-06, | |
| "loss": 2.7642, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 1.0005882352941176e-06, | |
| "loss": 2.7677, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.1823529411764706e-07, | |
| "loss": 2.7626, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4089445254884035, | |
| "eval_loss": 3.4202394485473633, | |
| "eval_runtime": 154.4184, | |
| "eval_samples_per_second": 375.072, | |
| "eval_steps_per_second": 5.861, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 372000, | |
| "total_flos": 1.56732865394688e+18, | |
| "train_loss": 3.0576216975386425, | |
| "train_runtime": 80892.0203, | |
| "train_samples_per_second": 147.156, | |
| "train_steps_per_second": 4.599 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 372000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 5000, | |
| "total_flos": 1.56732865394688e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |